Transform Weather Sensor Data from Waggle to an Xarray Dataset + Plot with ACT

Imports

import sage_data_client
from bokeh.models.formatters import DatetimeTickFormatter
import hvplot.pandas
import hvplot.xarray
import holoviews as hv
import cartopy.crs as ccrs
import cartopy.feature as cfeature
import xarray as xr
import matplotlib.pyplot as plt
from metpy.plots import USCOUNTIES
import act
import numpy as np
import pandas as pd
import warnings
from bokeh.models import DatetimeTickFormatter

def apply_formatter(plot, element):
    plot.handles['xaxis'].formatter = DatetimeTickFormatter(hours='%m/%d/%Y \n %H:%M',
                                                            minutes='%m/%d/%Y \n %H:%M',
                                                            hourmin='%m/%d/%Y \n %H:%M',
                                                            days='%m/%d/%Y \n %H:%M',
                                                            months='%m/%d/%Y \n %H:%M')
xr.set_options(keep_attrs=True)
warnings.filterwarnings("ignore")
hv.extension("bokeh")

Query for the available Data

wxt_df = sage_data_client.query(
    start="-3h",
    filter={
        "sensor": "vaisala-wxt536"
    }
)

Configure Helper Functions and Renaming Conventions

The renaming is required due to . notations being problematic when working with both Pandas and Xarray data structures.

variable_rename_dict = {'wxt.env.humidity':'air_humidity',
                        'wxt.env.pressure':'air_pressure',
                        'wxt.env.temp':'air_temperature',
                        'wxt.heater.temp':'heater_temperature',
                        'wxt.heater.volt':'heater_voltage',
                        'wxt.rain.accumulation':'rain_accumulation',
                        'wxt.wind.direction':'wind_direction',
                        'wxt.wind.speed':'wind_speed',
                        'sys.gps.lat':'latitude',
                        'sys.gps.lon':'longitude',
                    }

def generate_data_array(df, variable, rename_variable_dict=variable_rename_dict):
    new_variable_name = rename_variable_dict[variable]
    df_variable= df.loc[df.name == variable]
    ds = df_variable.to_xarray().rename({'value':new_variable_name,
                                         'timestamp':'time',
                                         'meta.vsn':'node'})
    ds[new_variable_name].attrs['units'] = df_variable['meta.units'].values[0]
    ds['time'] = pd.to_datetime(ds.time)
    ds.attrs['datastream'] = ds.node.values[0]
    return ds[[new_variable_name]]

def generate_dataset(df, variables, rename_variable_dict=variable_rename_dict):
    reindexed = df.set_index(['meta.vsn', 'timestamp'])
    return xr.merge([generate_data_array(reindexed, variable) for variable in variables])

Transform the Data to Xarray

wxt_variables = wxt_df.name.unique()
wxt_variables

array(['wxt.env.humidity', 'wxt.env.pressure', 'wxt.env.temp',
       'wxt.heater.temp', 'wxt.heater.volt', 'wxt.rain.accumulation',
       'wxt.wind.direction', 'wxt.wind.speed'], dtype=object)

wxt_ds = generate_dataset(wxt_df, wxt_variables).squeeze()
wxt_ds

<xarray.Dataset>
Dimensions:             (node: 2, time: 151009)
Coordinates:
  * node                (node) object 'W01B' 'W067'
  * time                (time) datetime64[ns] 2023-10-31T11:21:54.617147746 ....
Data variables:
    air_humidity        (node, time) float64 85.3 85.3 85.3 ... nan 100.0 nan
    air_pressure        (node, time) float64 1.005e+03 1.005e+03 ... 975.8 nan
    air_temperature     (node, time) float64 -2.7 -2.7 -2.7 ... nan -1.2 nan
    heater_temperature  (node, time) float64 2.1 2.1 2.1 2.1 ... nan 14.7 nan
    heater_voltage      (node, time) float64 11.3 11.3 11.3 ... nan 10.7 nan
    rain_accumulation   (node, time) float64 64.86 64.86 64.86 ... nan 25.98 nan
    wind_direction      (node, time) float64 130.0 130.0 130.0 ... nan 53.0 nan
    wind_speed          (node, time) float64 1.1 1.1 1.1 1.1 ... 0.2 nan 0.2 nan
Attributes:
    datastream:  W01B

xarray.Dataset

• Dimensions:
  • node: 2
  • time: 151009
• Coordinates: (2)
  • node
    (node)
    object
    'W01B' 'W067'

    array(['W01B', 'W067'], dtype=object)

  • time
    (time)
    datetime64[ns]
    2023-10-31T11:21:54.617147746 .....

    array(['2023-10-31T11:21:54.617147746', '2023-10-31T11:21:54.702979054',
           '2023-10-31T11:21:54.779118077', ..., '2023-10-31T14:21:54.844168952',
           '2023-10-31T14:21:54.897218446', '2023-10-31T14:21:54.919199937'],
          dtype='datetime64[ns]')

• Data variables: (8)
  • air_humidity
    (node, time)
    float64
    85.3 85.3 85.3 ... nan 100.0 nan

    units :

    percent

    array([[ 85.3,  85.3,  85.3, ...,   nan,   nan,   nan],
           [  nan,   nan,   nan, ...,   nan, 100. ,   nan]])

  • air_pressure
    (node, time)
    float64
    1.005e+03 1.005e+03 ... 975.8 nan

    units :

    hectoPascal

    array([[1004.9, 1004.9, 1004.9, ..., 1006.5,    nan, 1006.5],
           [   nan,    nan,    nan, ...,    nan,  975.8,    nan]])

  • air_temperature
    (node, time)
    float64
    -2.7 -2.7 -2.7 ... nan -1.2 nan

    units :

    degree Celsius

    array([[-2.7, -2.7, -2.7, ...,  0.4,  nan,  0.4],
           [ nan,  nan,  nan, ...,  nan, -1.2,  nan]])

  • heater_temperature
    (node, time)
    float64
    2.1 2.1 2.1 2.1 ... nan 14.7 nan

    units :

    degree Celsius

    array([[ 2.1,  2.1,  2.1, ...,  6.1,  nan,  6.1],
           [ nan,  nan,  nan, ...,  nan, 14.7,  nan]])

  • heater_voltage
    (node, time)
    float64
    11.3 11.3 11.3 ... nan 10.7 nan

    units :

    volts

    array([[11.3, 11.3, 11.3, ..., 11.3,  nan, 11.3],
           [ nan,  nan,  nan, ...,  nan, 10.7,  nan]])

  • rain_accumulation
    (node, time)
    float64
    64.86 64.86 64.86 ... nan 25.98 nan

    units :

    milimeters

    array([[64.86, 64.86, 64.86, ..., 64.86,   nan, 64.86],
           [  nan,   nan,   nan, ...,   nan, 25.98,   nan]])

  • wind_direction
    (node, time)
    float64
    130.0 130.0 130.0 ... nan 53.0 nan

    units :

    degrees

    array([[130., 130., 130., ..., 208.,  nan, 208.],
           [ nan,  nan,  nan, ...,  nan,  53.,  nan]])

  • wind_speed
    (node, time)
    float64
    1.1 1.1 1.1 1.1 ... 0.2 nan 0.2 nan

    units :

    meters per second

    array([[1.1, 1.1, 1.1, ..., 1.2, nan, 1.2],
           [nan, nan, nan, ..., nan, 0.2, nan]])

• Indexes: (2)
  • node
    PandasIndex

    PandasIndex(Index(['W01B', 'W067'], dtype='object', name='node'))

  • time
    PandasIndex

    PandasIndex(DatetimeIndex(['2023-10-31 11:21:54.617147746',
                   '2023-10-31 11:21:54.702979054',
                   '2023-10-31 11:21:54.779118077',
                   '2023-10-31 11:21:54.854512578',
                   '2023-10-31 11:21:54.940085578',
                   '2023-10-31 11:21:55.015381775',
                   '2023-10-31 11:21:55.090572689',
                   '2023-10-31 11:21:55.166106649',
                   '2023-10-31 11:21:55.241241435',
                   '2023-10-31 11:21:55.316475870',
                   ...
                   '2023-10-31 14:21:54.595453235',
                   '2023-10-31 14:21:54.605103162',
                   '2023-10-31 14:21:54.671195021',
                   '2023-10-31 14:21:54.680008641',
                   '2023-10-31 14:21:54.746603363',
                   '2023-10-31 14:21:54.755692562',
                   '2023-10-31 14:21:54.821744727',
                   '2023-10-31 14:21:54.844168952',
                   '2023-10-31 14:21:54.897218446',
                   '2023-10-31 14:21:54.919199937'],
                  dtype='datetime64[ns]', name='time', length=151009, freq=None))

• Attributes: (1)

  datastream :

  W01B

Resample the data to minute requency

minute_ds = wxt_ds.resample(time='1T').mean()

Visualize using hvplot

meteogram_variables = ['air_temperature', 'air_humidity', 'wind_speed', 'wind_direction']
plots = []
for variable in meteogram_variables:
    plots.append(wxt_ds[variable].hvplot.line(label='10 Hz Data') * 
                 minute_ds[variable].hvplot.line(label='1 Minute Data'))
hv.Layout(plots).cols(2)

Plot Using the Atmospheric Data Community Toolkit (ACT)

WindDisplay = act.plotting.WindRoseDisplay(minute_ds, figsize=(8, 10), subplot_shape=(1,))
WindDisplay.plot(
    'wind_direction', 'wind_speed', spd_bins=np.linspace(0, 25, 5), num_dirs=30, tick_interval=2, subplot_index=(0,)
)

<PolarAxes: title={'center': 'W01B on 20231031'}>